Reordering is currently one of the most important problems in statistical machine translation systems. This paper presents a novel strategy for dealing with it: statistical machine reordering (SMR). It consists in using the powerful techniques developed for statistical machine translation (SMT) to translate the source language (S) into a reordered source language (S’), which allows for an improved translation into the target language (T). The SMT task changes from S2T to S’2T which leads to a monotonized word alignment and shorter translation units. In addition, the use of classes in SMR helps to infer new word reorderings. Experiments are reported in the EsEn WMT06 tasks and the ZhEn IWSLT05 task and show significant improvement in translation quality. 1

This paper presents a full experiment on large-vocabulary Catalan-English statistical machine translation without an English-Catalan parallel corpus, in the context of the debates of the European Parliament. For this, we make use of an English-Spanish European Parliament Proceedings parallel corpus and a Spanish-Catalan general newspaper parallel corpus, both of which of more than 30 M words. Given the language proximity between Spanish and Catalan languages, we investigate the cost of using Spanish as a bridge towards large-vocabulary Catalan-English translation in a wholly automatical statistical machine translation framework. Experimental results are promising, as the achieved translation quality is nearly equivalent to that of the Spanish-English language pair, practically carrying SMT research for the Catalan language to the level of more prominent language, in terms of data availability. 1.

This paper studies a strategy for identifying and using multi-word expressions in Statistical Machine Translation. The performance of the proposed strategy for various types of multi-word expressions (like nouns or verbs) is evaluated in terms of alignment quality as well as translation accuracy. Evaluations are performed by using real-life data, namely the European Parliament corpus. Results from translation tasks from English-to-Spanish and from Spanish-to-English are presented and discussed. 1

Abstract. This paper presents a wide range of statistical word alignment experiments incorporating morphosyntactic information. By means of parallel corpus transformations according to information of POS-tagging, lemmatization or stemming, we explore which linguistic information helps improve alignment error rates. For this, evaluation against a human word alignment reference is performed, aiming at an improved machine translation training scheme which eventually leads to improved SMT performance. Experiments are carried out in a Spanish–English European Parliament Proceedings parallel corpus, both in a large and a small data track. As expected, improvements due to introducing morphosyntactic information are bigger in case of data scarcity, but significant improvement is also achieved in a large data task, meaning that certain linguistic knowledge is relevant even in situations of large data availability. 1